StereoSet: Measuring stereotypical bias in pretrained language models
This addresses the issue of harmful stereotypes in AI models for researchers and developers, though it is incremental as it builds on existing bias quantification efforts.
The authors tackled the problem of measuring stereotypical bias in pretrained language models by introducing StereoSet, a large-scale natural dataset in English across four domains, and found that popular models like BERT and GPT-2 exhibit strong biases.
A stereotype is an over-generalized belief about a particular group of people, e.g., Asians are good at math or Asians are bad drivers. Such beliefs (biases) are known to hurt target groups. Since pretrained language models are trained on large real world data, they are known to capture stereotypical biases. In order to assess the adverse effects of these models, it is important to quantify the bias captured in them. Existing literature on quantifying bias evaluates pretrained language models on a small set of artificially constructed bias-assessing sentences. We present StereoSet, a large-scale natural dataset in English to measure stereotypical biases in four domains: gender, profession, race, and religion. We evaluate popular models like BERT, GPT-2, RoBERTa, and XLNet on our dataset and show that these models exhibit strong stereotypical biases. We also present a leaderboard with a hidden test set to track the bias of future language models at https://stereoset.mit.edu